© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 113638
    Prev
    Next
    INDEX
    Explanations

    Technical/code related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ">"
    -0.07
    รด
    -0.07
    urous
    -0.06
     directed
    -0.06
    _scheduler
    -0.06
    زل
    -0.06
     manifestations
    -0.06
    、一
    -0.06
     Positive
    -0.06
     MID
    -0.06
    POSITIVE LOGITS
    _InitStructure
    0.07
     Argentina
    0.07
     possibly
    0.06
     aggregator
    0.06
     водой
    0.06
     düşün
    0.06
     inability
    0.06
    Autowired
    0.06
     gaussian
    0.06
    모
    0.06
    Activations Density 0.000%

    No Known Activations